freehire
freehire is an open-source job search engine that indexes tech jobs directly from company career boards. It offers a public API plus a CLI and MCP server so AI agents can search jobs without a browser.
Visit strelov1/freehireOverview
freehire indexes millions of tech jobs directly from company career boards, deduplicates them, and tags them by stack, seniority, and location. It combines a hosted search site with a keyless public HTTP API, a CLI, an MCP server, and a Chrome side-panel extension for search and application workflows.
Key Features
- Crawls job listings directly from company ATS platforms and career sites, links to original postings, and deduplicates reposts.
- Provides faceted full-text search over region, work mode, seniority, skills, and salary.
- Exposes a keyless public HTTP API for jobs and companies.
- Ships a CLI and an MCP server so AI agents and terminal users can search jobs without a browser.
- Includes a Chrome side-panel extension that reads postings, scores them against a CV, and fills application forms.
- Supports self-hosting with Go, PostgreSQL with pgvector, Meilisearch, Redis, and Docker Compose.
Use Cases
- Job seekers browsing and filtering tech roles indexed from company career boards.
- Developers and AI agents querying the public API or using the CLI and MCP server to run job searches.
- Teams self-hosting their own instance of the job catalogue and search stack.
- Candidates using the Chrome extension to assess and apply to postings on any site.
Getting Started
- Run make up to build and start the whole Docker stack, then check the health endpoint at localhost:8080/health and the jobs API at localhost:8080/api/v1/jobs.
- Install the CLI using the published install script; the CLI ships with agent skills for Claude Code and MCP hosts.
- For local development, start only the database with docker compose up -d db and run the server on the host with make run.
Deployment & Requirements
- Docker Compose for the full local stack: api, web, postgres, meilisearch, redis, and s3.
- PostgreSQL with pgvector, Meilisearch, Redis, and S3-compatible object storage as core dependencies.
- JWT_SECRET is required for the server to start; OAuth and LLM credentials are optional.
- Migrations apply automatically on first Postgres volume init; changed migrations require recreating the volume or running make migrate.
Before You Adopt
- License: MIT. Review its terms before using, modifying, or distributing the project.